October 15, 2019

1990 words 10 mins read

Paper Group NANR 240

Paper Group NANR 240

A High-Quality Gold Standard for Citation-based Tasks. A Challenge Set and Methods for Noun-Verb Ambiguity. SParse: Ko\cc University Graph-Based Parsing System for the CoNLL 2018 Shared Task. Complex Word Identification Based on Frequency in a Learner Corpus. Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-b …

A High-Quality Gold Standard for Citation-based Tasks

Title A High-Quality Gold Standard for Citation-based Tasks
Authors Michael F{"a}rber, Alex Thiemann, er, Adam Jatowt
Abstract
Tasks Entity Linking, Entity Resolution
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1296/
PDF https://www.aclweb.org/anthology/L18-1296
PWC https://paperswithcode.com/paper/a-high-quality-gold-standard-for-citation
Repo
Framework

A Challenge Set and Methods for Noun-Verb Ambiguity

Title A Challenge Set and Methods for Noun-Verb Ambiguity
Authors Ali Elkahky, Kellie Webster, Daniel Andor, Emily Pitler
Abstract English part-of-speech taggers regularly make egregious errors related to noun-verb ambiguity, despite having achieved 97{%}+ accuracy on the WSJ Penn Treebank since 2002. These mistakes have been difficult to quantify and make taggers less useful to downstream tasks such as translation and text-to-speech synthesis. This paper creates a new dataset of over 30,000 naturally-occurring non-trivial examples of noun-verb ambiguity. Taggers within 1{%} of each other when measured on the WSJ have accuracies ranging from 57{%} to 75{%} accuracy on this challenge set. Enhancing the strongest existing tagger with contextual word embeddings and targeted training data improves its accuracy to 89{%}, a 14{%} absolute (52{%} relative) improvement. Downstream, using just this enhanced tagger yields a 28{%} reduction in error over the prior best learned model for homograph disambiguation for textto-speech synthesis.
Tasks Speech Synthesis, Text-To-Speech Synthesis, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1277/
PDF https://www.aclweb.org/anthology/D18-1277
PWC https://paperswithcode.com/paper/a-challenge-set-and-methods-for-noun-verb
Repo
Framework

SParse: Ko\cc University Graph-Based Parsing System for the CoNLL 2018 Shared Task

Title SParse: Ko\cc University Graph-Based Parsing System for the CoNLL 2018 Shared Task
Authors Berkay {"O}nder, Can G{"u}meli, Deniz Yuret
Abstract We present SParse, our Graph-Based Parsing model submitted for the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (Zeman et al., 2018). Our model extends the state-of-the-art biaffine parser (Dozat and Manning, 2016) with a structural meta-learning module, SMeta, that combines local and global label predictions. Our parser has been trained and run on Universal Dependencies datasets (Nivre et al., 2016, 2018) and has 87.48{%} LAS, 78.63{%} MLAS, 78.69{%} BLEX and 81.76{%} CLAS (Nivre and Fang, 2017) score on the Italian-ISDT dataset and has 72.78{%} LAS, 59.10{%} MLAS, 61.38{%} BLEX and 61.72{%} CLAS score on the Japanese-GSD dataset in our official submission. All other corpora are evaluated after the submission deadline, for whom we present our unofficial test results.
Tasks Dependency Parsing, Language Modelling, Meta-Learning, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-2022/
PDF https://www.aclweb.org/anthology/K18-2022
PWC https://paperswithcode.com/paper/sparse-koa-university-graph-based-parsing
Repo
Framework

Complex Word Identification Based on Frequency in a Learner Corpus

Title Complex Word Identification Based on Frequency in a Learner Corpus
Authors Tomoyuki Kajiwara, Mamoru Komachi
Abstract We introduce the TMU systems for the Complex Word Identification (CWI) Shared Task 2018. TMU systems use random forest classifiers and regressors whose features are the number of characters, the number of words, and the frequency of target words in various corpora. Our simple systems performed best on 5 tracks out of 12 tracks. Our ablation analysis revealed the usefulness of a learner corpus for CWI task.
Tasks Complex Word Identification, Lexical Simplification, Reading Comprehension, Text Simplification
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0521/
PDF https://www.aclweb.org/anthology/W18-0521
PWC https://paperswithcode.com/paper/complex-word-identification-based-on
Repo
Framework

Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-based Modeling

Title Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-based Modeling
Authors Hiroaki Santo, Michael Waechter, Masaki Samejima, Yusuke Sugano, Yasuyuki Matsushita
Abstract We present a practical method for geometric point light source calibration. Unlike in prior works that use Lambertian spheres, mirror spheres, or mirror planes, our calibration target consists of a Lambertian plane and small shadow casters at unknown positions above the plane. Due to their small size, the casters’ shadows can be localized more precisely than highlights on mirrors. We show that, given shadow observations from a moving calibration target and a fixed camera, the shadow caster positions and the light position or direction can be simultaneously recovered in a structure from motion framework. Our evaluation on simulated and real scenes shows that our method yields light estimates that are stable and more accurate than existing techniques while having a considerably simpler setup and requiring less manual labor.
Tasks Calibration
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Hiroaki_Santo_Light_Structure_from_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Hiroaki_Santo_Light_Structure_from_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/light-structure-from-pin-motion-simple-and
Repo
Framework

A Spectral Approach to Generalization and Optimization in Neural Networks

Title A Spectral Approach to Generalization and Optimization in Neural Networks
Authors Farzan Farnia, Jesse Zhang, David Tse
Abstract The recent success of deep neural networks stems from their ability to generalize well on real data; however, Zhang et al. have observed that neural networks can easily overfit random labels. This observation demonstrates that with the existing theory, we cannot adequately explain why gradient methods can find generalizable solutions for neural networks. In this work, we use a Fourier-based approach to study the generalization properties of gradient-based methods over 2-layer neural networks with sinusoidal activation functions. We prove that if the underlying distribution of data has nice spectral properties such as bandlimitedness, then the gradient descent method will converge to generalizable local minima. We also establish a Fourier-based generalization bound for bandlimited spaces, which generalizes to other activation functions. Our generalization bound motivates a grouped version of path norms for measuring the complexity of 2-layer neural networks with ReLU activation functions. We demonstrate numerically that regularization of this group path norm results in neural network solutions that can fit true labels without losing test accuracy while not overfitting random labels.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=HJBhEMbRb
PDF https://openreview.net/pdf?id=HJBhEMbRb
PWC https://paperswithcode.com/paper/a-spectral-approach-to-generalization-and
Repo
Framework

AntNLP at CoNLL 2018 Shared Task: A Graph-Based Parser for Universal Dependency Parsing

Title AntNLP at CoNLL 2018 Shared Task: A Graph-Based Parser for Universal Dependency Parsing
Authors Tao Ji, Yufang Liu, Yijun Wang, Yuanbin Wu, Man Lan
Abstract We describe the graph-based dependency parser in our system (AntNLP) submitted to the CoNLL 2018 UD Shared Task. We use bidirectional lstm to get the word representation, then a bi-affine pointer networks to compute scores of candidate dependency edges and the MST algorithm to get the final dependency tree. From the official testing results, our system gets 70.90 LAS F1 score (rank 9/26), 55.92 MLAS (10/26) and 60.91 BLEX (8/26).
Tasks Dependency Parsing
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-2025/
PDF https://www.aclweb.org/anthology/K18-2025
PWC https://paperswithcode.com/paper/antnlp-at-conll-2018-shared-task-a-graph
Repo
Framework

Hybed: Hyperbolic Neural Graph Embedding

Title Hybed: Hyperbolic Neural Graph Embedding
Authors Benjamin Paul Chamberlain, James R Clough, Marc Peter Deisenroth
Abstract Neural embeddings have been used with great success in Natural Language Processing (NLP) where they provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of linguistic tasks. The success of neural embeddings has prompted significant amounts of research into applications in domains other than language. One such domain is graph-structured data, where embeddings of vertices can be learned that encapsulate vertex similarity and improve performance on tasks including edge prediction and vertex labelling. For both NLP and graph-based tasks, embeddings in high-dimensional Euclidean spaces have been learned. However, recent work has shown that the appropriate isometric space for embedding complex networks is not the flat Euclidean space, but a negatively curved hyperbolic space. We present a new concept that exploits these recent insights and propose learning neural embeddings of graphs in hyperbolic space. We provide experimental evidence that hyperbolic embeddings significantly outperform Euclidean embeddings on vertex classification tasks for several real-world public datasets.
Tasks Graph Embedding
Published 2018-01-01
URL https://openreview.net/forum?id=S1xDcSR6W
PDF https://openreview.net/pdf?id=S1xDcSR6W
PWC https://paperswithcode.com/paper/hybed-hyperbolic-neural-graph-embedding
Repo
Framework

Finding the way from "a to a: Sub-character morphological inflection for the SIGMORPHON 2018 shared task

Title Finding the way from "a to a: Sub-character morphological inflection for the SIGMORPHON 2018 shared task
Authors Fynn Schr{"o}der, Marcel Kamlot, Gregor Billing, Arne K{"o}hn
Abstract
Tasks Morphological Inflection
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-3009/
PDF https://www.aclweb.org/anthology/K18-3009
PWC https://paperswithcode.com/paper/finding-the-way-from-a-to-a-sub-character
Repo
Framework

Training Binary Weight Networks via Semi-Binary Decomposition

Title Training Binary Weight Networks via Semi-Binary Decomposition
Authors Qinghao Hu, Gang Li, Peisong Wang, Yifan Zhang, Jian Cheng
Abstract Recently binary weight networks have attracted lots of attentions due to their high computational efficiency and small parameter size. Yet they still suffer from large accuracy drops because of their limited representation capacity. In this paper, we propose a novel semi-binary decomposition method which decomposes a matrix into two binary matrices and a diagonal matrix. Since the matrix product of binary matrices has more numerical values than binary matrix, the proposed semi-binary decomposition has more representation capacity. Besides, we propose an alternating optimization method to solve the semi-binary decomposition problem while keeping binary constraints. Extensive experiments on AlexNet, ResNet-18, and ResNet-50 demonstrate that our method outperforms state-of-the-art methods by a large margin (5 percentage higher in top1 accuracy). We also implement binary weight AlexNet on FPGA platform, which shows that our proposed method can achieve $sim 9 imes$ speed-ups while reducing the consumption of on-chip memory and dedicated multipliers significantly.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Qinghao_Hu_Training_Binary_Weight_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Qinghao_Hu_Training_Binary_Weight_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/training-binary-weight-networks-via-semi
Repo
Framework

Semantic role labeling tools for biomedical question answering: a study of selected tools on the BioASQ datasets

Title Semantic role labeling tools for biomedical question answering: a study of selected tools on the BioASQ datasets
Authors Fabian Eckert, Mariana Neves
Abstract Question answering (QA) systems usually rely on advanced natural language processing components to precisely understand the questions and extract the answers. Semantic role labeling (SRL) is known to boost performance for QA, but its use for biomedical texts has not yet been fully studied. We analyzed the performance of three SRL tools (BioKIT, BIOSMILE and PathLSTM) on 1776 questions from the BioASQ challenge. We compared the systems regarding the coverage of the questions and snippets, as well as based on pre-defined criteria, such as easiness of installation, supported formats and usability. Finally, we integrated two of the tools in a simple QA system to further evaluate their performance over the official BioASQ test sets.
Tasks Named Entity Recognition, Part-Of-Speech Tagging, Question Answering, Semantic Parsing, Semantic Role Labeling
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5302/
PDF https://www.aclweb.org/anthology/W18-5302
PWC https://paperswithcode.com/paper/semantic-role-labeling-tools-for-biomedical
Repo
Framework

Open ASR for Icelandic: Resources and a Baseline System

Title Open ASR for Icelandic: Resources and a Baseline System
Authors Anna Bj{"o}rk Nikul{'a}sd{'o}ttir, Inga R{'u}n Helgad{'o}ttir, Matth{'\i}as P{'e}tursson, J{'o}n Gu{\dh}nason
Abstract
Tasks Language Modelling, Large Vocabulary Continuous Speech Recognition, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1495/
PDF https://www.aclweb.org/anthology/L18-1495
PWC https://paperswithcode.com/paper/open-asr-for-icelandic-resources-and-a
Repo
Framework

Syntactic Category Learning as Iterative Prototype-Driven Clustering

Title Syntactic Category Learning as Iterative Prototype-Driven Clustering
Authors Jordan Kodner
Abstract
Tasks Part-Of-Speech Tagging
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0305/
PDF https://www.aclweb.org/anthology/W18-0305
PWC https://paperswithcode.com/paper/syntactic-category-learning-as-iterative
Repo
Framework

Proceedings of The Third Workshop on Representation Learning for NLP

Title Proceedings of The Third Workshop on Representation Learning for NLP
Authors
Abstract
Tasks Representation Learning
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3000/
PDF https://www.aclweb.org/anthology/W18-3000
PWC https://paperswithcode.com/paper/proceedings-of-the-third-workshop-on
Repo
Framework

Stochastic Nonparametric Event-Tensor Decomposition

Title Stochastic Nonparametric Event-Tensor Decomposition
Authors Shandian Zhe, Yishuai Du
Abstract Tensor decompositions are fundamental tools for multiway data analysis. Existing approaches, however, ignore the valuable temporal information along with data, or simply discretize them into time steps so that important temporal patterns are easily missed. Moreover, most methods are limited to multilinear decomposition forms, and hence are unable to capture intricate, nonlinear relationships in data. To address these issues, we formulate event-tensors, to preserve the complete temporal information for multiway data, and propose a novel Bayesian nonparametric decomposition model. Our model can (1) fully exploit the time stamps to capture the critical, causal/triggering effects between the interaction events, (2) flexibly estimate the complex relationships between the entities in tensor modes, and (3) uncover hidden structures from their temporal interactions. For scalable inference, we develop a doubly stochastic variational Expectation-Maximization algorithm to conduct an online decomposition. Evaluations on both synthetic and real-world datasets show that our model not only improves upon the predictive performance of existing methods, but also discovers interesting clusters underlying the data.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7918-stochastic-nonparametric-event-tensor-decomposition
PDF http://papers.nips.cc/paper/7918-stochastic-nonparametric-event-tensor-decomposition.pdf
PWC https://paperswithcode.com/paper/stochastic-nonparametric-event-tensor
Repo
Framework
comments powered by Disqus